WO2020138603A1 - Digital twin system and method for optimizing control scenario of mechanical device - Google Patents

Digital twin system and method for optimizing control scenario of mechanical device Download PDF

Info

Publication number
WO2020138603A1
WO2020138603A1 PCT/KR2019/007424 KR2019007424W WO2020138603A1 WO 2020138603 A1 WO2020138603 A1 WO 2020138603A1 KR 2019007424 W KR2019007424 W KR 2019007424W WO 2020138603 A1 WO2020138603 A1 WO 2020138603A1
Authority
WO
WIPO (PCT)
Prior art keywords
control scenario
virtual model
mechanical device
digital twin
components
Prior art date
Application number
PCT/KR2019/007424
Other languages
French (fr)
Korean (ko)
Inventor
김호원
강효은
Original Assignee
부산대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 부산대학교 산학협력단 filed Critical 부산대학교 산학협력단
Publication of WO2020138603A1 publication Critical patent/WO2020138603A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the present invention relates to a digital twin system and method for optimizing a control scenario of a mechanical device, and more particularly, a system and method for automatically generating an optimal control scenario of a mechanical device using a virtual model simulating a real mechanical device It is about.
  • a simulator that can simulate the operation of a machine in a computing environment on behalf of the machine has been proposed.
  • a virtual model corresponding to a mechanical device is implemented.
  • Digital Twin is a concept advocated by General Electric (GE) in the United States, and is a technology that predicts results by creating virtual models that are twins with machinery and simulating situations that can occur in reality in virtual models. Digital twin is attracting attention as a technology that can solve various industrial and social problems as well as manufacturing.
  • GE General Electric
  • FIG. 1 is a configuration of a component control model of the prior art.
  • the virtual model shows the driving result as if the actual mechanical device was driven by the control scenario.
  • Conventional simulation technology has been able to confirm the driving process of components constituting a mechanical device.
  • the conventional simulation technique only shows the operation result of the virtual model corresponding to the modified parameter, and the control scenario cannot be improved or optimized by itself.
  • the simulation technology is driven based on the operation data collected in advance, the driving method of the virtual model cannot be changed in response to the control scenario changed in real time.
  • the present invention is to solve the above problems, and an object of the present invention is to provide a system and method for automatically generating an optimal control scenario of a machine using a virtual model simulating a real machine.
  • An object of the present invention is to provide a digital twin system and method for optimizing a control scenario of a mechanical device that enables a real-world system and a digital twin simulator to interwork with an IoT platform in operating mechanical equipment.
  • a digital twin simulator actively evolves a model for a major component of a mechanical equipment, and at the same time, enables a real mechanical equipment system and a digital twin simulator to be managed in an optimal or desired control manner, thereby improving production efficiency.
  • the purpose is to provide a digital twin system and method for optimizing the control scenario of the device.
  • the digital twin system for optimizing the control scenario of the machine for achieving the above object is an IoT device that receives the operation information of the machine, and controls the operation of the machine in response to the control scenario, and It characterized in that it comprises a virtual model that simulates the mechanical device, and a digital twin device that corrects a control scenario using the virtual model and delivers the corrected control scenario to the IoT device.
  • the operation information includes operation information for each component of the mechanical device
  • the virtual model may include a component corresponding to a component of the mechanical device.
  • the digital twin device including the virtual model; A model control unit controlling the virtual model to be operated in the same manner as the mechanical device; And a policy optimization unit that optimizes the control scenario using a virtual model controlled by the model control unit.
  • the model control unit checks whether a component of the virtual model outputs the same operation information as a component of the mechanical device, and if there is a difference, the component can output the same operation information as a component of the mechanical device. It can be characterized by updating the parameters of the component.
  • the policy optimization unit may receive a user's control scenario, transmit the input user's control scenario to the simulation unit, and the simulation unit operates a virtual model in response to the user's control scenario to obtain driving result information. It can be characterized by outputting.
  • the digital twin method for optimizing the control scenario of the mechanical device according to the present invention for achieving the above object is a digital twin device generating a virtual model that simulates the mechanical device; An IoT device driving the mechanical device based on an existing control scenario; Controlling the operation of the virtual model such that the operation information of the components of the mechanical device and the components of the virtual model coincides with the digital twin device; Generating, by the digital twin device, an optimized control scenario using the driving information of the virtual model, and transmitting it to the IoT device; And the IoT device driving the mechanical device using the optimized control scenario.
  • the step of controlling the operation of the virtual model so that the operation information of the components of the mechanical device and the components of the virtual model coincide with the digital twin device is to determine whether the state of the virtual model and the mechanical device match. step; Checking whether a component part of the virtual model outputs the same operation information as a component of the mechanical device; And when there is a difference in the operation information, updating the parameters of the component unit so that the component unit outputs the same operation information as the components of the mechanical device.
  • the digital twin device using the operation information of the virtual model to generate an optimized control scenario, and transmitting to the IoT device comprises: checking whether the virtual model is changed; When the virtual model is changed, generating a control scenario using the virtual model; Checking whether the control scenario is suitable; And when the control scenario is suitable, passing the control scenario to the IoT device.
  • the digital twin simulator actively evolves the model for the major components of the mechanical equipment, and at the same time, it enables the actual mechanical equipment system and the digital twin simulator to be managed in an optimal or desired control manner, thereby improving production efficiency.
  • FIG. 1 is a block diagram of a conventional simulation system.
  • FIG. 2 is a block diagram of a digital twin system for optimizing a control scenario of a mechanical device according to an embodiment of the present invention.
  • FIG. 3 is a flowchart of a digital twin method for optimizing a control scenario of a mechanical device according to an embodiment of the present invention.
  • Figure 4 is a flow chart specifically showing the step S150.
  • step S160 is a flowchart specifically showing step S160.
  • the digital twin system for optimizing the control scenario of the machine 100 receives the operation information of the machine 100, and corresponds to the control scenario, the machine 100 ) To drive the IoT device 300.
  • It also includes a virtual model that simulates the mechanical device 100, and a digital twin device 200 that corrects a control scenario using the virtual model and delivers the corrected control scenario to the IoT device 300.
  • the mechanical device 100 may be a single device or a set of devices driven in an environment such as a manufacturing process or a power plant in reality.
  • the components of the machine 100 include equipment elements physically driven by the actuator, power elements related to power supplied or output to the machine 100, and resource elements related to resources consumed by the machine 100. do.
  • the mechanical device 100 further includes a plurality of sensors that detect the state of equipment elements, power elements, and resource elements, and generate respective operation information.
  • the IoT (Internet of Things) device 300 receives driving information measured by a sensor of the mechanical device 100 and controls driving of the mechanical device 100 using the driving information.
  • the IoT device 300 transmits information between the mechanical device 100 and the digital twin device 200.
  • the IoT device 300 collects the sensor values of the components of the mechanical device 100, that is, the components, and transmits the sensor values of the components to the digital twin device 200 at regular intervals.
  • the IoT device 300 includes an operation information storage unit 350 in which information such as the operation information value of the machine device 100, control commands transmitted to the machine device 100, feedback of the machine device 100, and the like is stored. .
  • the IoT device 300 includes an operation control unit 320 that controls the operation of the mechanical device 100.
  • the IoT device 300 includes a policy setting unit 310 for setting a control scenario.
  • the control scenario includes a method in which the operation control unit 320 controls the operation of the mechanical device 100.
  • the IoT device 300 includes a rights management unit 330 that manages control rights of components of the mechanical device 100.
  • the digital twin is a technology that virtually creates twins that mimic the reality mechanism 100 and simulates a situation that may occur in reality with a computer.
  • the combination of data and information representing the structure, context, and operation of various physical systems enables understanding of past and present operational conditions.
  • the digital twin device 200 includes a simulation unit 210 including a virtual model that simulates the operation of the mechanical device 100 in a virtual environment.
  • the virtual model of the digital twin device 200 not only simulates the operation of the mechanical device 100, but also finds an improved driving control method, and uses this information to optimize the control scenario to optimize the driving performance of the actual mechanical device 100. Improves.
  • the simulation unit 210 includes a monitoring unit 212 that checks whether the state of the machine 100 and the virtual model match.
  • the state of the machine 100 and the virtual model is the state of the main component to be monitored among the components of the machine 100, that is, operation information.
  • the operation information may include a fuel injection amount, an exhaust gas amount, and a standby state.
  • performance efficiency, flow rate function, fuel cost, etc. can be additionally calculated using the operation information obtained from the gas turbine.
  • the monitoring unit 212 extracts driving information of the same type as the mechanical device 100 from the virtual model, and compares the driving information of the mechanical device 100 with the driving information of the virtual model to check whether the state matches. In addition, the monitoring unit 212 generates information such as performance efficiency, flow rate function, fuel cost, etc. generated using the operation information of the mechanical device 100 using operation information of the virtual model, and the mechanical device 100 and the virtual model It is checked whether the state is consistent by comparing the performance efficiency, flow rate function, and fuel cost information.
  • the driving information generated by the sensor included in the mechanical device 100 includes driving information for each component of the mechanical device 100.
  • the simulation unit 210 includes a component unit 214 corresponding to the components of the mechanical device 100.
  • the component unit 214 includes components that simulate virtually the operation of the components of the machine 100.
  • the component unit 214 is formed in a plurality in correspondence with the number of components of the machine 100.
  • the digital twin device 200 includes a model control unit 230 that controls the virtual model of the simulation unit 210 to operate in the same manner as the mechanical device 100.
  • the model control unit 230 checks whether the components of the virtual model output the same operation information as the components of the mechanical device 100.
  • the model control unit 230 is a parameter of the component unit 214 that determines a method for controlling the operation of the component so that the component can output the same operation information when there is a difference between the operation information of the component and the operation information of the component of the mechanical device 100. Adjust the operating model of the component by updating.
  • the model control unit 230 may generate parameter update information of the component unit 214 using a machine learning algorithm.
  • the digital twin device 200 includes a policy optimization unit 240 that optimizes a control scenario using a virtual model controlled by the model control unit 230.
  • the policy optimization unit 240 optimizes the control scenario of the machine 100 using the component unit 214 whose parameters are updated.
  • the policy optimization unit 240 generates a corresponding new control scenario when the state of the virtual model changes for reasons such as parameter update of the component unit 214. In addition, the suitability of the generated new control scenario is checked, and the optimization method is fed back.
  • the conformity check of the new control scenario confirms whether the maintenance performance conforms to the operation and maintenance policy of the machine 100 when the control scenario is applied to the machine 100. For example, after a new control scenario is applied, information such as anomaly detection, expected operating time and expected operating time, and expected energy consumption of the machine 100 are calculated, and the result value exceeds a predetermined criterion. It is judged to be suitable only when possible.
  • the optimization method of the control scenario predicts the occurrence of fatigue cracks, abrasion, deterioration, etc. when the control scenario is applied using the failure prediction and health management technology, and countermeasures to prevent the predicted failure Is to present.
  • the policy optimization unit 240 checks whether the virtual model has been changed. When the virtual model is changed, a new control scenario is generated using information such as parameters of the changed virtual model. In addition, it is determined whether the new control scenario is a suitable control scenario. If it is determined that the new control scenario is suitable, the new control scenario is transmitted to the policy setting unit 310 of the IoT device 300.
  • the policy optimization unit 240 may generate a control scenario using a machine learning algorithm.
  • the policy optimization unit 240 may receive a user's control scenario directly input by the administrator.
  • the policy optimization unit 240 transmits the input user control scenario to the simulation unit 210.
  • the simulation unit 210 controls the operation of the virtual model in response to the user's control scenario.
  • the simulation unit 210 outputs operation result information of the controlled virtual model in response to the user's control scenario.
  • the digital twin device 200 includes a control monitoring unit 250 that checks whether the scenario for driving the mechanical device 100 and the scenario for driving the virtual model match.
  • the control monitoring unit 250 checks whether the control scenarios coincide to prevent damage that may occur according to the operation modes of the current mechanical device 100 and the digital twin device 200. For example, in a gas turbine, when a load cutoff occurs during operation, and a sudden load reduction occurs, a control scenario is prepared to suppress the overspeed of the gas turbine and maintain the required minimum power. Therefore, when the operation mode is changed by the simulation unit 210 by the control of the model control unit 230, it is necessary to include a suitable control scenario.
  • the operation control unit 320 of the IoT device 300 controls the operation of the mechanical device 100 in response to the new control scenario of the policy setting unit 310.
  • the operation control unit 320 obtains control authority for the components of the mechanical device 100 using the authority management unit 330.
  • the scenario included in the policy setting unit 310 of the IoT device 300 determines a control method of the mechanical device 100.
  • the initial control scenario may be set as a standard control scenario provided by the machine 100 manufacturer.
  • the policy setting unit 310 receives the new control scenario generated by the policy optimization unit 240 and replaces the existing control scenario.
  • the policy setting unit 310 provides a new control scenario replaced by the operation control unit 320 so that the operation control unit 320 can operate the machine 100 according to the new control scenario.
  • the digital twin device 200 generates a virtual model that mimics the mechanical device 100 (S120), and the IoT device 300 is based on an existing control scenario.
  • the twin device 200 generates an optimized control scenario using the driving information of the virtual model, and transmits it to the IoT device 300 (S160), and the machine using the optimized control scenario for the IoT device 300 It includes the step of driving the device 100 (S180).
  • step S150 is specifically, the step of checking whether the state of the virtual machine and the virtual machine 100 (S152), the component part 214 of the virtual model and the components of the machine 100 The step of confirming whether the same operation information is output (S154), and when there is a difference in operation information (S155), the component unit so that the component unit 214 can output the same operation information as the components of the mechanical device 100. And updating the parameter of step 214 (S156).
  • the parameter of the component unit 214 is not updated.
  • step S160 is specifically, checking whether the virtual model is changed (S162), when the virtual model is changed (S163), and generating a control scenario using the virtual model (S164), control It includes the step of checking whether the scenario is suitable (S166), if the control scenario is suitable (S167), and transmitting the control scenario to the IoT device 300 (S168).
  • the present invention relates to a digital twin system and method for optimizing a control scenario of a mechanical device, and more particularly, a system and method for automatically generating an optimal control scenario of a mechanical device using a virtual model simulating a real mechanical device It is about.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Manufacturing & Machinery (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The present invention relates to a system and a method for automatically creating an optimal control scenario of a mechanical device by using a virtual model that simulates an actual mechanical device, the system comprising: an IoT device for receiving operation information of the mechanical device and controlling the operation of the mechanical device according to the control scenario; and a digital twin device, which includes the virtual model for imitating the mechanical device, corrects the control scenario by using the virtual model, and transmits the corrected control scenario to the IoT device.

Description

기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법 Digital twin system and method to optimize the control scenario of machinery
본 발명은 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법에 관한 것으로, 더욱 상세하게는 실제 기계장치를 모사하는 가상모델을 이용하여 자동으로 기계장치의 최적의 제어 시나리오를 생성하는 시스템 및 방법에 관한 것이다.The present invention relates to a digital twin system and method for optimizing a control scenario of a mechanical device, and more particularly, a system and method for automatically generating an optimal control scenario of a mechanical device using a virtual model simulating a real mechanical device It is about.
제조공정, 발전소 등에서 이용되는 기계장치는 고 비용이다. 따라서 변경된 제어 시나리오를 시험 없이 기계장치에 적용하면 고장이나 사고가 발생될 수 있다.Machinery used in manufacturing processes and power plants is expensive. Therefore, if the changed control scenario is applied to the machine without testing, a failure or accident may occur.
따라서 기계장치를 대신하여 컴퓨팅 환경 내에서 가상으로 기계장치의 운전을 시뮬레이션 할 수 있는 시뮬레이터가 제안되었다. 시뮬레이터에는 기계장치에 대응되는 가상모델이 구현된다.Therefore, a simulator that can simulate the operation of a machine in a computing environment on behalf of the machine has been proposed. In the simulator, a virtual model corresponding to a mechanical device is implemented.
특히, 시뮬레이션 기술로서 디지털트윈(digital twin)이 제안되었다. 디지털트윈은 미국 제너럴 일렉트릭(GE)이 주창한 개념으로, 기계장치와 쌍둥이가 되는 가상모델을 만들고, 현실에서 발생할 수 있는 상황을 가상모델에서 시뮬레이션 함으로써 결과를 예측하는 기술이다. 디지털트윈은 제조업 뿐만 아니라 다양한 산업, 사회 문제를 해결할 수 있는 기술로 주목받고 있다.In particular, a digital twin has been proposed as a simulation technology. Digital Twin is a concept advocated by General Electric (GE) in the United States, and is a technology that predicts results by creating virtual models that are twins with machinery and simulating situations that can occur in reality in virtual models. Digital twin is attracting attention as a technology that can solve various industrial and social problems as well as manufacturing.
도 1은 종래기술의 컴포넌트 제어모델의 구성이다. 가상모델에 제어 시나리오를 적용하면, 가상모델은 실제 기계장치가 해당 제어 시나리오에 의해 구동된 것과 같은 운전 결과를 보여준다. 종래의 시뮬레이션 기술은 기계장치를 구성하는 구성요소(components)의 구동 과정을 확인할 수 있었다.1 is a configuration of a component control model of the prior art. When a control scenario is applied to the virtual model, the virtual model shows the driving result as if the actual mechanical device was driven by the control scenario. Conventional simulation technology has been able to confirm the driving process of components constituting a mechanical device.
그러나, 종래의 시뮬레이션 기술은 수정된 파라미터에 대응하는 가상모델의 운전 결과만을 보여줄 뿐, 제어 시나리오를 스스로 개선하거나 최적화할 수 없었다. 또한 시뮬레이션 기술은 사전에 수집한 운영 데이터에 기반하여 구동되기 때문에 실시간으로 변경된 제어 시나리오에 대응하여 가상모델의 운전 방법이 변경될 수 없었다. However, the conventional simulation technique only shows the operation result of the virtual model corresponding to the modified parameter, and the control scenario cannot be improved or optimized by itself. In addition, since the simulation technology is driven based on the operation data collected in advance, the driving method of the virtual model cannot be changed in response to the control scenario changed in real time.
본 발명은 상기와 같은 문제를 해결하기 위한 것으로, 본 발명의 목적은 실제 기계장치를 모사하는 가상모델을 이용하여 자동으로 기계장치의 최적의 제어 시나리오를 생성하는 시스템 및 방법을 제공함에 있다.The present invention is to solve the above problems, and an object of the present invention is to provide a system and method for automatically generating an optimal control scenario of a machine using a virtual model simulating a real machine.
본 발명은 기계장비를 운영하는데 있어서 IoT 플랫폼으로 실제 시스템과 디지털트윈 시뮬레이터를 연동할 수 있도록 한 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법을 제공하는데 그 목적이 있다.An object of the present invention is to provide a digital twin system and method for optimizing a control scenario of a mechanical device that enables a real-world system and a digital twin simulator to interwork with an IoT platform in operating mechanical equipment.
본 발명은 기계장비 주요 컴포넌트에 대해 디지털트윈 시뮬레이터가 능동적으로 모델을 진화시키고, 동시에 실제 기계장비 시스템과 디지털트윈 시뮬레이터를 최적 혹은 원하는 제어방식으로 관리할 수 있도록 하여 생산효율을 향상시킬 수 있도록 한 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법을 제공하는데 그 목적이 있다.In the present invention, a digital twin simulator actively evolves a model for a major component of a mechanical equipment, and at the same time, enables a real mechanical equipment system and a digital twin simulator to be managed in an optimal or desired control manner, thereby improving production efficiency. The purpose is to provide a digital twin system and method for optimizing the control scenario of the device.
상기와 같은 목적을 달성하기 위한 본 발명에 따른 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템은 기계장치의 운전정보를 수신하고, 제어 시나리오에 대응하여 상기 기계장치의 운전을 제어하는 IoT장치, 및 상기 기계장치를 모사하는 가상모델을 포함하고, 상기 가상모델을 이용하여 제어 시나리오를 보정하고, 보정된 제어 시나리오를 상기 IoT장치에 전달하는 디지털트윈장치를 포함하는 것을 특징으로 한다.The digital twin system for optimizing the control scenario of the machine according to the present invention for achieving the above object is an IoT device that receives the operation information of the machine, and controls the operation of the machine in response to the control scenario, and It characterized in that it comprises a virtual model that simulates the mechanical device, and a digital twin device that corrects a control scenario using the virtual model and delivers the corrected control scenario to the IoT device.
또한, 상기 운전정보에는 기계장치의 구성요소 별 운전정보가 포함되고, 상기 가상모델은 상기 기계장치의 구성요소에 대응하는 컴포넌트를 포함하는 것을 특징으로 할 수 있다.In addition, the operation information includes operation information for each component of the mechanical device, and the virtual model may include a component corresponding to a component of the mechanical device.
또한, 상기 디지털트윈장치는, 상기 가상모델을 포함하는 시뮬레이션부; 상기 가상모델을 상기 기계장치와 동일하게 운전되게 제어하는 모델제어부; 및 상기 모델제어부가 제어하는 가상모델을 이용하여 상기 제어 시나리오를 최적화하는 정책최적화부를 포함하는 것을 특징으로 할 수 있다.In addition, the digital twin device, the simulation unit including the virtual model; A model control unit controlling the virtual model to be operated in the same manner as the mechanical device; And a policy optimization unit that optimizes the control scenario using a virtual model controlled by the model control unit.
또한, 상기 모델제어부는 상기 가상모델의 컴포넌트가 상기 기계장치의 구성요소와 동일한 운전정보를 출력하는지 확인하고, 차이가 있으면 상기 컴포넌트가 상기 기계장치의 구성요소와 동일한 운전정보를 출력할 수 있게 상기 컴포넌트의 파라미터를 업데이트하는 것을 특징으로 할 수 있다.In addition, the model control unit checks whether a component of the virtual model outputs the same operation information as a component of the mechanical device, and if there is a difference, the component can output the same operation information as a component of the mechanical device. It can be characterized by updating the parameters of the component.
또한, 상기 정책최적화부는 사용자의 제어 시나리오를 입력 받을 수 있고, 입력된 사용자의 제어 시나리오를 상기 시뮬레이션부에 전달하며, 상기 시뮬레이션부는 상기 사용자의 제어 시나리오에 대응하여 가상모델을 운전하여 운전결과정보를 출력하는 것을 특징으로 할 수 있다.In addition, the policy optimization unit may receive a user's control scenario, transmit the input user's control scenario to the simulation unit, and the simulation unit operates a virtual model in response to the user's control scenario to obtain driving result information. It can be characterized by outputting.
한편, 상기와 같은 목적을 달성하기 위한 본 발명에 따른 기계장치의 제어 시나리오를 최적화하는 디지털트윈 방법은 디지털트윈장치가 기계장치를 모사하는 가상모델을 생성하는 단계; IoT장치가 기존 제어 시나리오에 기반하여 상기 기계장치를 운전하는 단계; 상기 디지털트윈장치가 상기 기계장치의 구성요소와 상기 가상모델의 컴포넌트의 운전정보가 일치되게 상기 가상모델의 운전을 제어하는 단계; 상기 디지털트윈장치가 상기 가상모델의 운전정보를 이용하여 최적화된 제어 시나리오를 생성하고, 상기 IoT장치로 전달하는 단계; 및 상기 IoT장치가 상기 최적화된 제어 시나리오를 이용하여 상기 기계장치를 운전하는 단계를 포함하는 것을 특징으로 한다.On the other hand, the digital twin method for optimizing the control scenario of the mechanical device according to the present invention for achieving the above object is a digital twin device generating a virtual model that simulates the mechanical device; An IoT device driving the mechanical device based on an existing control scenario; Controlling the operation of the virtual model such that the operation information of the components of the mechanical device and the components of the virtual model coincides with the digital twin device; Generating, by the digital twin device, an optimized control scenario using the driving information of the virtual model, and transmitting it to the IoT device; And the IoT device driving the mechanical device using the optimized control scenario.
또한, 상기 디지털트윈장치가 상기 기계장치의 구성요소와 상기 가상모델의 컴포넌트의 운전정보가 일치되게 상기 가상모델의 운전을 제어하는 단계는, 상기 기계장치와 상기 가상모델의 상태 일치 여부를 확인하는 단계; 상기 가상모델의 컴포넌트부가 상기 기계장치의 구성요소와 동일한 운전정보를 출력하는지 확인하는 단계; 및 운전정보에서 차이가 있는 경우, 컴포넌트부가 기계장치의 구성요소와 동일한 운전정보를 출력할 수 있게 컴포넌트부의 파라미터를 업데이트하는 단계를 포함하는 것을 특징으로 할 수 있다.In addition, the step of controlling the operation of the virtual model so that the operation information of the components of the mechanical device and the components of the virtual model coincide with the digital twin device is to determine whether the state of the virtual model and the mechanical device match. step; Checking whether a component part of the virtual model outputs the same operation information as a component of the mechanical device; And when there is a difference in the operation information, updating the parameters of the component unit so that the component unit outputs the same operation information as the components of the mechanical device.
또한, 상기 디지털트윈장치가 상기 가상모델의 운전정보를 이용하여 최적화된 제어 시나리오를 생성하고, 상기 IoT장치로 전달하는 단계는, 상기 가상모델의 변경 여부를 확인하는 단계; 상기 가상모델이 변경된 경우, 상기 가상모델을 이용하여 제어 시나리오를 생성하는 단계; 상기 제어 시나리오의 적합 여부를 검사하는 단계; 및 상기 제어 시나리오가 적합한 경우, 상기 제어 시나리오를 상기 IoT장치로 전달하는 단계를 포함하는 것을 특징으로 할 수 있다.In addition, the digital twin device using the operation information of the virtual model to generate an optimized control scenario, and transmitting to the IoT device comprises: checking whether the virtual model is changed; When the virtual model is changed, generating a control scenario using the virtual model; Checking whether the control scenario is suitable; And when the control scenario is suitable, passing the control scenario to the IoT device.
본 발명의 실시예에 의한 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법에 따르면,According to a digital twin system and method for optimizing a control scenario of a mechanical device according to an embodiment of the present invention,
첫째, 실제 기계장치를 모사하는 가상모델을 이용하여 자동으로 기계장치의 최적의 제어 시나리오를 생성할 수 있도록 한다.First, it is possible to automatically generate an optimal control scenario of the machine using a virtual model that simulates a real machine.
둘째, 실제 기계장치와 연결된 IoT 플랫폼과 연동되는 디지털트윈을 구현하여 기계장치의 주요 구성요소를 대상으로 최적화된 제어 시나리오를 제공할 수 있게 된다.Second, it is possible to provide an optimized control scenario targeting the major components of the machine by implementing a digital twin that is linked to the IoT platform connected to the actual machine.
셋째, 기계장치와 동일하게 구동하는 가상모델을 구축하고, 가상모델에서 최적화가 검증된 시나리오를 기계장치에 적용하므로, 변경된 시나리오에 의해 기계장치에서 오류가 발생하는 것을 방지할 수 있고, 기계장치의 효율을 극대화시킬 수 있게 된다.Third, since a virtual model that operates in the same manner as the mechanical device is built, and the scenario in which the optimization is verified in the virtual model is applied to the mechanical device, errors in the mechanical device can be prevented due to the changed scenario. The efficiency can be maximized.
넷째, 기계장비 주요 컴포넌트에 대해 디지털트윈 시뮬레이터가 능동적으로 모델을 진화시키고, 동시에 실제 기계장비 시스템과 디지털트윈 시뮬레이터를 최적 혹은 원하는 제어방식으로 관리할 수 있도록 하여 생산효율을 향상시킬 수 있도록 한다.Fourth, the digital twin simulator actively evolves the model for the major components of the mechanical equipment, and at the same time, it enables the actual mechanical equipment system and the digital twin simulator to be managed in an optimal or desired control manner, thereby improving production efficiency.
도 1은 종래 시뮬레이션 시스템의 구성도.1 is a block diagram of a conventional simulation system.
도 2는 본 발명의 실시예에 따른 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템의 구성도.2 is a block diagram of a digital twin system for optimizing a control scenario of a mechanical device according to an embodiment of the present invention.
도 3은 본 발명의 실시예에 따른 기계장치의 제어 시나리오를 최적화하는 디지털트윈 방법의 순서도.3 is a flowchart of a digital twin method for optimizing a control scenario of a mechanical device according to an embodiment of the present invention.
도 4는 S150 단계를 구체적으로 나타낸 순서도.Figure 4 is a flow chart specifically showing the step S150.
도 5는 S160 단계를 구체적으로 나타낸 순서도.5 is a flowchart specifically showing step S160.
이하 첨부된 도면을 참조하여 본 발명에 따른 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법의 바람직한 실시예를 상세히 설명한다.Hereinafter, preferred embodiments of a digital twin system and method for optimizing a control scenario of a mechanical device according to the present invention will be described in detail with reference to the accompanying drawings.
도 2를 참조하면, 본 발명의 실시예에 따른 기계장치(100)의 제어 시나리오를 최적화하는 디지털트윈 시스템은 기계장치(100)의 운전정보를 수신하고, 제어 시나리오에 대응하여 상기 기계장치(100)를 구동시키는 IoT장치(300)를 포함한다.2, the digital twin system for optimizing the control scenario of the machine 100 according to an embodiment of the present invention receives the operation information of the machine 100, and corresponds to the control scenario, the machine 100 ) To drive the IoT device 300.
또한 기계장치(100)를 모사하는 가상모델을 포함하고, 가상모델을 이용하여 제어 시나리오를 보정하고, 보정된 제어 시나리오를 IoT장치(300)에 전달하는 디지털트윈장치(200)를 포함한다.It also includes a virtual model that simulates the mechanical device 100, and a digital twin device 200 that corrects a control scenario using the virtual model and delivers the corrected control scenario to the IoT device 300.
기계장치(100)는 현실의 제조공정, 발전소 등 환경에서 구동되는 단일 장치 또는 장치들의 집합이 될 수 있다. 기계장치(100)의 구성요소에는 액추에이터에 의해 물리적으로 구동되는 장비요소, 기계장치(100)에 공급 또는 출력되는 전력과 관련된 전원요소, 기계장치(100)가 소모하는 자원과 관련된 자원요소를 포함한다. 또한 기계장치(100)는 장비요소, 전원요소, 자원요소의 상태를 감지하여 각각의 운전정보를 생성하는 복수의 센서를 더 포함한다.The mechanical device 100 may be a single device or a set of devices driven in an environment such as a manufacturing process or a power plant in reality. The components of the machine 100 include equipment elements physically driven by the actuator, power elements related to power supplied or output to the machine 100, and resource elements related to resources consumed by the machine 100. do. In addition, the mechanical device 100 further includes a plurality of sensors that detect the state of equipment elements, power elements, and resource elements, and generate respective operation information.
IoT(Internet of Things)장치(300)는 기계장치(100)의 센서가 계측한 운전정보를 수신하고, 운전정보를 이용하여 기계장치(100)의 구동을 제어한다. IoT장치(300)는 기계장치(100)와 디지털트윈장치(200) 간의 정보를 전달한다. IoT장치(300)는 기계장치(100)의 구성요소, 즉 컴포넌트의 센서 값을 수집하고, 컴포넌트의 센서 값을 일정 주기로 디지털트윈장치(200)에 전달한다.The IoT (Internet of Things) device 300 receives driving information measured by a sensor of the mechanical device 100 and controls driving of the mechanical device 100 using the driving information. The IoT device 300 transmits information between the mechanical device 100 and the digital twin device 200. The IoT device 300 collects the sensor values of the components of the mechanical device 100, that is, the components, and transmits the sensor values of the components to the digital twin device 200 at regular intervals.
IoT장치(300)는 기계장치(100)의 운전정보 값, 기계장치(100)에 전달된 제어 명령, 기계장치(100)의 피드백 등의 정보가 저장되는 운전정보저장부(350)를 포함한다.The IoT device 300 includes an operation information storage unit 350 in which information such as the operation information value of the machine device 100, control commands transmitted to the machine device 100, feedback of the machine device 100, and the like is stored. .
IoT장치(300)는 기계장치(100)의 운전을 제어하는 운전제어부(320)를 포함한다.The IoT device 300 includes an operation control unit 320 that controls the operation of the mechanical device 100.
IoT장치(300)는 제어 시나리오를 설정하는 정책설정부(310)를 포함한다. 제어 시나리오에는 운전제어부(320)가 기계장치(100)의 운전을 제어하는 방법이 포함된다.The IoT device 300 includes a policy setting unit 310 for setting a control scenario. The control scenario includes a method in which the operation control unit 320 controls the operation of the mechanical device 100.
IoT장치(300)는 기계장치(100) 구성요소의 제어 권한을 관리하는 권한관리부(330)를 포함한다.The IoT device 300 includes a rights management unit 330 that manages control rights of components of the mechanical device 100.
디지털트윈이란, 가상으로 현실 기계장치(100)를 모사하는 쌍둥이를 만들고, 현실에서 발생할 수 있는 상황을 컴퓨터로 시뮬레이션 할 수 있는 기술이다. 다양한 물리적 시스템의 구조, 맥락, 작동을 나타내는 데이터와 정보의 조합으로, 과거와 현재의 운용 상태를 이해할 수 있다.The digital twin is a technology that virtually creates twins that mimic the reality mechanism 100 and simulates a situation that may occur in reality with a computer. The combination of data and information representing the structure, context, and operation of various physical systems enables understanding of past and present operational conditions.
디지털트윈장치(200)는 가상 환경에서 기계장치(100)의 운전을 모사하는 가상모델이 포함된 시뮬레이션부(210)를 포함한다.The digital twin device 200 includes a simulation unit 210 including a virtual model that simulates the operation of the mechanical device 100 in a virtual environment.
디지털트윈장치(200)의 가상모델은 기계장치(100)의 운전을 모사할 뿐만 아니라, 개선된 운전 제어방법을 찾고, 이 정보를 이용하여 제어 시나리오를 최적화하여 실제 기계장치(100)의 구동 성능을 향상시킨다.The virtual model of the digital twin device 200 not only simulates the operation of the mechanical device 100, but also finds an improved driving control method, and uses this information to optimize the control scenario to optimize the driving performance of the actual mechanical device 100. Improves.
시뮬레이션부(210)는 기계장치(100)와 가상모델의 상태 일치 여부를 확인하는 모니터링부(212)를 포함한다. 기계장치(100)와 가상모델의 상태는 기계장치(100)의 구성요소 중 모니터링 대상이 되는 주요 구성요소의 상태, 즉 운전정보이다. 예를 들어, 기계장치(100)가 가스터빈인 경우, 운전정보에는 연료주입량, 배출가스량, 대기상태가 포함될 수 있다. 또한 가스터빈에서 획득된 운전정보를 이용하여 성능효율, 유량함수, 연료비 등을 추가 연산할 수 있다.The simulation unit 210 includes a monitoring unit 212 that checks whether the state of the machine 100 and the virtual model match. The state of the machine 100 and the virtual model is the state of the main component to be monitored among the components of the machine 100, that is, operation information. For example, when the mechanical device 100 is a gas turbine, the operation information may include a fuel injection amount, an exhaust gas amount, and a standby state. In addition, performance efficiency, flow rate function, fuel cost, etc. can be additionally calculated using the operation information obtained from the gas turbine.
모니터링부(212)는 가상모델에서 기계장치(100)와 동일한 종류의 운전정보를 추출하고, 기계장치(100)의 운전정보와 가상모델의 운전정보를 비교하는 것으로 상태 일치 여부를 확인한다. 또한 모니터링부(212)는 기계장치(100)의 운전정보를 이용하여 생성된 성능효율, 유량함수, 연료비 등의 정보를 가상모델의 운전정보를 이용하여 생성하고, 기계장치(100)와 가상모델의 성능효율, 유량함수, 연료비 정보를 비교하는 것으로 상태 일치 여부를 확인한다.The monitoring unit 212 extracts driving information of the same type as the mechanical device 100 from the virtual model, and compares the driving information of the mechanical device 100 with the driving information of the virtual model to check whether the state matches. In addition, the monitoring unit 212 generates information such as performance efficiency, flow rate function, fuel cost, etc. generated using the operation information of the mechanical device 100 using operation information of the virtual model, and the mechanical device 100 and the virtual model It is checked whether the state is consistent by comparing the performance efficiency, flow rate function, and fuel cost information.
기계장치(100)에 포함된 센서에서 생성되는 운전정보에는 기계장치(100)의 구성요소 별 운전정보가 포함된다.The driving information generated by the sensor included in the mechanical device 100 includes driving information for each component of the mechanical device 100.
시뮬레이션부(210)는 기계장치(100)의 구성요소에 대응하는 컴포넌트부(214)를 포함한다. 컴포넌트부(214)에는 기계장치(100) 구성요소의 동작을 가상으로 모사하는 컴포넌트가 포함된다. 컴포넌트부(214)는 기계장치(100)의 구성요소 수에 대응하여 복수개로 형성된다.The simulation unit 210 includes a component unit 214 corresponding to the components of the mechanical device 100. The component unit 214 includes components that simulate virtually the operation of the components of the machine 100. The component unit 214 is formed in a plurality in correspondence with the number of components of the machine 100.
디지털트윈장치(200)는 시뮬레이션부(210)의 가상모델이 기계장치(100)와 동일하게 운전되게 제어하는 모델제어부(230)를 포함한다. 모델제어부(230)는 가상모델의 컴포넌트가 기계장치(100)의 구성요소와 동일한 운전정보를 출력하는지 확인한다. 모델제어부(230)는 컴포넌트의 운전정보와 기계장치(100) 구성요소의 운전정보에 차이가 있으면 컴포넌트가 동일한 운전정보를 출력할 수 있게 컴포넌트의 운전 제어방법을 결정하는 컴포넌트부(214)의 파라미터를 업데이트하는 것으로 컴포넌트의 운영모델을 조정한다.The digital twin device 200 includes a model control unit 230 that controls the virtual model of the simulation unit 210 to operate in the same manner as the mechanical device 100. The model control unit 230 checks whether the components of the virtual model output the same operation information as the components of the mechanical device 100. The model control unit 230 is a parameter of the component unit 214 that determines a method for controlling the operation of the component so that the component can output the same operation information when there is a difference between the operation information of the component and the operation information of the component of the mechanical device 100. Adjust the operating model of the component by updating.
모델제어부(230)는 머신러닝 알고리즘을 이용하여 컴포넌트부(214)의 파라미터 업데이트 정보를 생성할 수 있다.The model control unit 230 may generate parameter update information of the component unit 214 using a machine learning algorithm.
디지털트윈장치(200)는 모델제어부(230)가 제어하는 가상모델을 이용하여 제어 시나리오를 최적화하는 정책최적화부(240)를 포함한다. 정책최적화부(240)는 파라미터가 업데이트된 컴포넌트부(214)를 이용하여 기계장치(100)의 제어 시나리오를 최적화한다. 정책최적화부(240)는 컴포넌트부(214)의 파라미터 업데이트 등의 이유로 가상모델의 상태가 변화되면 대응되는 신규 제어 시나리오를 생성한다. 또한 생성된 신규 제어 시나리오의 적합성을 확인하고, 최적화 방안을 피드백 한다.The digital twin device 200 includes a policy optimization unit 240 that optimizes a control scenario using a virtual model controlled by the model control unit 230. The policy optimization unit 240 optimizes the control scenario of the machine 100 using the component unit 214 whose parameters are updated. The policy optimization unit 240 generates a corresponding new control scenario when the state of the virtual model changes for reasons such as parameter update of the component unit 214. In addition, the suitability of the generated new control scenario is checked, and the optimization method is fed back.
신규 제어 시나리오의 적합성 확인은 해당 제어 시나리오가 기계장치(100)에 적용된 경우, 정비 성능이 기계장치(100) 운영 및 정비 정책에 적합한지를 확인한다. 예를 들어, 신규 제어 시나리오가 적용된 후 기계장치(100)의 이상현상가능성(Anomaly Detection), 예상운전시간 및 예상가동시간, 예상 에너지 소모 등의 정보를 연산하고, 결과 값이 기 설정된 기준 이상이 되는 경우에만 적합한 것으로 판단한다.The conformity check of the new control scenario confirms whether the maintenance performance conforms to the operation and maintenance policy of the machine 100 when the control scenario is applied to the machine 100. For example, after a new control scenario is applied, information such as anomaly detection, expected operating time and expected operating time, and expected energy consumption of the machine 100 are calculated, and the result value exceeds a predetermined criterion. It is judged to be suitable only when possible.
제어 시나리오의 최적화 방안은 고장예지 및 건전성관리(Prognostics and Health Management) 기술을 이용하여 제어 시나리오가 적용되는 경우의 피로균열, 마모, 열화 등의 발생을 예측하고, 예측되는 고장을 방지하기 위한 대응방법을 제시하는 것이다. 피로균열, 마모, 열화 등의 발생 예측은 기 축적된 데이터를 기반으로 예측하는 방법과, 실제 고장이 발생된 사례의 데이터를 이용하는 예측 방법이 있다. The optimization method of the control scenario predicts the occurrence of fatigue cracks, abrasion, deterioration, etc. when the control scenario is applied using the failure prediction and health management technology, and countermeasures to prevent the predicted failure Is to present. There are two methods of predicting the occurrence of fatigue cracks, abrasion, and deterioration based on pre-accumulated data, and a prediction method using data of actual failure cases.
예를 들어, 정책최적화부(240)는 가상모델의 변경 여부를 확인한다. 가상모델이 변경되면, 변경된 가상모델의 파라미터 등의 정보를 이용하여 신규 제어 시나리오를 생성한다. 또한 신규 제어 시나리오가 적합한 제어 시나리오인지 적합성을 판단한다. 신규 제어 시나리오가 적합한 것으로 판단되면, 신규 제어 시나리오를 IoT장치(300)의 정책설정부(310)에 전달한다.For example, the policy optimization unit 240 checks whether the virtual model has been changed. When the virtual model is changed, a new control scenario is generated using information such as parameters of the changed virtual model. In addition, it is determined whether the new control scenario is a suitable control scenario. If it is determined that the new control scenario is suitable, the new control scenario is transmitted to the policy setting unit 310 of the IoT device 300.
정책최적화부(240)는 머신러닝 알고리즘을 이용하여 제어 시나리오를 생성할 수 있다.The policy optimization unit 240 may generate a control scenario using a machine learning algorithm.
정책최적화부(240)는 관리자가 직접 입력한 사용자의 제어 시나리오를 입력 받을 수 있다. 정책최적화부(240)는 입력된 사용자의 제어 시나리오를 시뮬레이션부(210)에 전달한다. 시뮬레이션부(210)는 사용자의 제어 시나리오에 대응하여 가상모델의 운전을 제어한다. 시뮬레이션부(210)는 사용자의 제어 시나리오에 대응하여 제어된 가상모델의 운전결과정보를 출력한다. The policy optimization unit 240 may receive a user's control scenario directly input by the administrator. The policy optimization unit 240 transmits the input user control scenario to the simulation unit 210. The simulation unit 210 controls the operation of the virtual model in response to the user's control scenario. The simulation unit 210 outputs operation result information of the controlled virtual model in response to the user's control scenario.
디지털트윈장치(200)는 기계장치(100)를 구동하는 시나리오와 가상모델을 구동하는 시나리오가 일치되는지 확인하는 제어감시부(250)를 포함한다. 제어감시부(250)는 현재 기계장치(100) 및 디지털트윈장치(200)의 운영모드에 따라 발생될 수 있는 피해를 예방하기 위해 제어 시나리오가 일치하는지 확인한다. 예를 들어, 가스터빈에서는 운영 중 부하차단이 발생되어 급격한 부하감소가 발생되면 가스터빈의 과속을 억제하고 필요최소출력을 유지하는 제어 시나리오가 마련된다. 따라서, 시뮬레이션부(210)가 모델제어부(230)의 조절에 의해 운영모드가 변경되면, 적합한 제어 시나리오를 포함해야 한다.The digital twin device 200 includes a control monitoring unit 250 that checks whether the scenario for driving the mechanical device 100 and the scenario for driving the virtual model match. The control monitoring unit 250 checks whether the control scenarios coincide to prevent damage that may occur according to the operation modes of the current mechanical device 100 and the digital twin device 200. For example, in a gas turbine, when a load cutoff occurs during operation, and a sudden load reduction occurs, a control scenario is prepared to suppress the overspeed of the gas turbine and maintain the required minimum power. Therefore, when the operation mode is changed by the simulation unit 210 by the control of the model control unit 230, it is necessary to include a suitable control scenario.
IoT장치(300)의 운전제어부(320)는 정책설정부(310)의 신규 제어 시나리오에 대응하여 기계장치(100)의 운전을 제어한다.The operation control unit 320 of the IoT device 300 controls the operation of the mechanical device 100 in response to the new control scenario of the policy setting unit 310.
운전제어부(320)는 권한관리부(330)를 이용하여 기계장치(100)의 구성요소에 대한 제어 권한을 획득한다.The operation control unit 320 obtains control authority for the components of the mechanical device 100 using the authority management unit 330.
IoT장치(300)의 정책설정부(310)에 포함된 시나리오는 기계장치(100)의 제어 방법을 결정한다. 초기의 제어 시나리오는 기계장치(100) 제조사에서 제공하는 표준 제어 시나리오로 설정될 수 있다. 정책설정부(310)는 정책최적화부(240)에서 생성된 신규 제어 시나리오를 전달받아 기존의 제어 시나리오를 대체한다. 정책설정부(310)는 운전제어부(320)에 대체된 신규 제어 시나리오를 제공하여 운전제어부(320)가 신규 제어 시나리오에 따라 기계장치(100)를 운전할 수 있게 한다.The scenario included in the policy setting unit 310 of the IoT device 300 determines a control method of the mechanical device 100. The initial control scenario may be set as a standard control scenario provided by the machine 100 manufacturer. The policy setting unit 310 receives the new control scenario generated by the policy optimization unit 240 and replaces the existing control scenario. The policy setting unit 310 provides a new control scenario replaced by the operation control unit 320 so that the operation control unit 320 can operate the machine 100 according to the new control scenario.
이어서, 본 발명의 실시예에 따른 기계장치(100)의 제어 시나리오를 최적화하는 디지털트윈 방법을 설명한다.Next, a digital twin method for optimizing a control scenario of the machine 100 according to an embodiment of the present invention will be described.
도 2를 참조하면, 이 실시예는 디지털트윈장치(200)가 기계장치(100)를 모사하는 가상모델을 생성하는 단계(S120), IoT장치(300)가 기존 제어 시나리오에 기반하여 기계장치(100)를 운전하는 단계(S140), 디지털트윈장치(200)가 기계장치(100)의 구성요소와 가상모델의 컴포넌트의 운전정보가 일치되게 상기 가상모델의 운전을 제어하는 단계(S150), 디지털트윈장치(200)가 가상모델의 운전정보를 이용하여 최적화된 제어 시나리오를 생성하고, IoT장치(300)로 전달하는 단계(S160), 및 IoT장치(300)가 최적화된 제어 시나리오를 이용하여 기계장치(100)를 운전하는 단계(S180)를 포함한다.Referring to FIG. 2, in this embodiment, the digital twin device 200 generates a virtual model that mimics the mechanical device 100 (S120), and the IoT device 300 is based on an existing control scenario. 100) driving (S140), the digital twin device 200 controlling the operation of the virtual model such that the operation information of the components of the mechanical device 100 and the components of the virtual model (S150), digital The twin device 200 generates an optimized control scenario using the driving information of the virtual model, and transmits it to the IoT device 300 (S160), and the machine using the optimized control scenario for the IoT device 300 It includes the step of driving the device 100 (S180).
도 3을 참조하면, S150 단계는 구체적으로, 기계장치(100)와 가상모델의 상태 일치 여부를 확인하는 단계(S152), 가상모델의 컴포넌트부(214)가 기계장치(100)의 구성요소와 동일한 운전정보를 출력하는지 확인하는 단계(S154), 및 운전정보에서 차이가 있는 경우(S155), 컴포넌트부(214)가 기계장치(100)의 구성요소와 동일한 운전정보를 출력할 수 있게 컴포넌트부(214)의 파라미터를 업데이트하는 단계(S156)를 포함한다.Referring to Figure 3, step S150 is specifically, the step of checking whether the state of the virtual machine and the virtual machine 100 (S152), the component part 214 of the virtual model and the components of the machine 100 The step of confirming whether the same operation information is output (S154), and when there is a difference in operation information (S155), the component unit so that the component unit 214 can output the same operation information as the components of the mechanical device 100. And updating the parameter of step 214 (S156).
만약 운전정보에서 차이가 없는 경우(S155), 컴포넌트부(214)의 파라미터를 업데이트하지 않는다.If there is no difference in the driving information (S155), the parameter of the component unit 214 is not updated.
도 4를 참조하면, S160 단계는 구체적으로, 가상모델의 변경 여부를 확인하는 단계(S162), 가상모델이 변경된 경우(S163), 가상모델을 이용하여 제어 시나리오를 생성하는 단계(S164), 제어 시나리오의 적합 여부를 검사하는 단계(S166), 제어 시나리오가 적합한 경우(S167), 제어 시나리오를 IoT장치(300)로 전달하는 단계(S168)를 포함한다.Referring to FIG. 4, step S160 is specifically, checking whether the virtual model is changed (S162), when the virtual model is changed (S163), and generating a control scenario using the virtual model (S164), control It includes the step of checking whether the scenario is suitable (S166), if the control scenario is suitable (S167), and transmitting the control scenario to the IoT device 300 (S168).
이상에서 본 발명은 실시예를 참조하여 상세히 설명되었으나, 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자라면 상기에서 설명된 기술적 사상을 벗어나지 않는 범위 내에서 여러 가지 치환, 부가 및 변형이 가능할 것임은 당연하며, 이와 같은 변형된 실시 형태들 역시 아래에 첨부한 특허청구범위에 의하여 정하여지는 본 발명의 보호 범위에 속하는 것으로 이해되어야 할 것이다.In the above, the present invention has been described in detail with reference to examples, but those skilled in the art to which the present invention pertains will be capable of various substitutions, additions, and modifications without departing from the technical spirit described above. Of course, it should be understood that these modified embodiments also belong to the protection scope of the present invention as defined by the appended claims.
본 발명은 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템 및 방법에 관한 것으로, 더욱 상세하게는 실제 기계장치를 모사하는 가상모델을 이용하여 자동으로 기계장치의 최적의 제어 시나리오를 생성하는 시스템 및 방법에 관한 것이다.The present invention relates to a digital twin system and method for optimizing a control scenario of a mechanical device, and more particularly, a system and method for automatically generating an optimal control scenario of a mechanical device using a virtual model simulating a real mechanical device It is about.

Claims (8)

  1. 기계장치의 운전정보를 수신하고, 제어 시나리오에 대응하여 상기 기계장치의 운전을 제어하는 IoT장치, 및IoT device that receives the operation information of the machine, and controls the operation of the machine in response to a control scenario, and
    상기 기계장치를 모사하는 가상모델을 포함하고, 상기 가상모델을 이용하여 제어 시나리오를 보정하고, 보정된 제어 시나리오를 상기 IoT장치에 전달하는 디지털트윈장치를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템.And a virtual twin device that simulates the mechanical device, corrects a control scenario using the virtual model, and includes a digital twin device that delivers the corrected control scenario to the IoT device. Digital twin system that optimizes.
  2. 제1항에 있어서,According to claim 1,
    상기 운전정보에는 기계장치의 구성요소 별 운전정보가 포함되고, 상기 가상모델은 상기 기계장치의 구성요소에 대응하는 컴포넌트를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템.The operation information includes operation information for each component of the mechanical device, and the virtual model includes a component corresponding to a component of the mechanical device.
  3. 제2항에 있어서, 상기 디지털트윈장치는,According to claim 2, The digital twin device,
    상기 가상모델을 포함하는 시뮬레이션부;A simulation unit including the virtual model;
    상기 가상모델을 상기 기계장치와 동일하게 운전되게 제어하는 모델제어부; 및 A model control unit controlling the virtual model to be operated in the same manner as the mechanical device; And
    상기 모델제어부가 제어하는 가상모델을 이용하여 상기 제어 시나리오를 최적화하는 정책최적화부를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템.And a policy optimization unit that optimizes the control scenario using a virtual model controlled by the model control unit.
  4. 제3항에 있어서,According to claim 3,
    상기 모델제어부는 상기 가상모델의 컴포넌트가 상기 기계장치의 구성요소와 동일한 운전정보를 출력하는지 확인하고, 차이가 있으면 상기 컴포넌트가 상기 기계장치의 구성요소와 동일한 운전정보를 출력할 수 있게 상기 컴포넌트의 파라미터를 업데이트하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템.The model control unit checks whether the components of the virtual model output the same operation information as the components of the mechanical device, and if there is a difference, the components can output the same operation information as the components of the mechanical device. A digital twin system that optimizes the control scenario of a machine, characterized by updating parameters.
  5. 제3항에 있어서,According to claim 3,
    상기 정책최적화부는 사용자의 제어 시나리오를 입력 받을 수 있고, 입력된 사용자의 제어 시나리오를 상기 시뮬레이션부에 전달하며,The policy optimization unit may receive a user's control scenario, and transmit the input user's control scenario to the simulation unit,
    상기 시뮬레이션부는 상기 사용자의 제어 시나리오에 대응하여 가상모델을 운전하여 운전결과정보를 출력하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 시스템.The simulation unit operates a virtual model in response to the user's control scenario and outputs operation result information. A digital twin system for optimizing a control scenario of a mechanical device.
  6. 디지털트윈장치가 기계장치를 모사하는 가상모델을 생성하는 단계;A digital twin device generating a virtual model simulating a mechanical device;
    IoT장치가 기존 제어 시나리오에 기반하여 상기 기계장치를 운전하는 단계;An IoT device driving the mechanical device based on an existing control scenario;
    상기 디지털트윈장치가 상기 기계장치의 구성요소와 상기 가상모델의 컴포넌트의 운전정보가 일치되게 상기 가상모델의 운전을 제어하는 단계;Controlling the operation of the virtual model such that the operation information of the components of the mechanical device and the components of the virtual model coincides with the digital twin device;
    상기 디지털트윈장치가 상기 가상모델의 운전정보를 이용하여 최적화된 제어 시나리오를 생성하고, 상기 IoT장치로 전달하는 단계; 및Generating, by the digital twin device, an optimized control scenario using the driving information of the virtual model, and transmitting it to the IoT device; And
    상기 IoT장치가 상기 최적화된 제어 시나리오를 이용하여 상기 기계장치를 운전하는 단계를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 방법.A digital twin method for optimizing a control scenario of a mechanical device, characterized in that the IoT device includes operating the mechanical device using the optimized control scenario.
  7. 제6항에 있어서, 상기 디지털트윈장치가 상기 기계장치의 구성요소와 상기 가상모델의 컴포넌트의 운전정보가 일치되게 상기 가상모델의 운전을 제어하는 단계는,The method of claim 6, wherein the step of controlling the operation of the virtual model so that the operation information of the components of the mechanical model and the components of the virtual model coincide with the digital twin device,
    상기 기계장치와 상기 가상모델의 상태 일치 여부를 확인하는 단계;Checking whether the state of the virtual model matches the mechanical device;
    상기 가상모델의 컴포넌트부가 상기 기계장치의 구성요소와 동일한 운전정보를 출력하는지 확인하는 단계; 및Checking whether a component part of the virtual model outputs the same operation information as a component of the mechanical device; And
    운전정보에서 차이가 있는 경우, 컴포넌트부가 기계장치의 구성요소와 동일한 운전정보를 출력할 수 있게 컴포넌트부의 파라미터를 업데이트하는 단계를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 방법.If there is a difference in the driving information, the digital twin method for optimizing the control scenario of the mechanical device, characterized in that it comprises the step of updating the parameters of the component unit so that the component unit can output the same operating information as the components of the mechanical device.
  8. 제6항에 있어서, 상기 디지털트윈 장치가 상기 가상모델의 운전정보를 이용하여 최적화된 제어 시나리오를 생성하고, 상기 IoT장치로 전달하는 단계는,The method of claim 6, wherein the digital twin device generates an optimized control scenario using the driving information of the virtual model, and transfers it to the IoT device.
    상기 가상모델의 변경 여부를 확인하는 단계;Checking whether the virtual model is changed;
    상기 가상모델이 변경된 경우, 상기 가상모델을 이용하여 제어 시나리오를 생성하는 단계;When the virtual model is changed, generating a control scenario using the virtual model;
    상기 제어 시나리오의 적합 여부를 검사하는 단계; 및Checking whether the control scenario is suitable; And
    상기 제어 시나리오가 적합한 경우, 상기 제어 시나리오를 상기 IoT장치로 전달하는 단계를 포함하는 것을 특징으로 하는 기계장치의 제어 시나리오를 최적화하는 디지털트윈 방법.And if the control scenario is suitable, transmitting the control scenario to the IoT device.
PCT/KR2019/007424 2018-12-27 2019-06-20 Digital twin system and method for optimizing control scenario of mechanical device WO2020138603A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020180171175A KR20200081066A (en) 2018-12-27 2018-12-27 Digital-twin system and method for optimizes the driving scenarios of a mechanical equipment
KR10-2018-0171175 2018-12-27

Publications (1)

Publication Number Publication Date
WO2020138603A1 true WO2020138603A1 (en) 2020-07-02

Family

ID=71127159

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2019/007424 WO2020138603A1 (en) 2018-12-27 2019-06-20 Digital twin system and method for optimizing control scenario of mechanical device

Country Status (2)

Country Link
KR (1) KR20200081066A (en)
WO (1) WO2020138603A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131782A (en) * 2020-08-27 2020-12-25 浙江大学 Multi-loop intelligent factory edge side digital twin scene coupling device

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102398416B1 (en) * 2020-07-28 2022-05-16 재단법인대구경북과학기술원 Digital twinning method for electrode
KR102365369B1 (en) * 2020-07-30 2022-02-22 한국해양대학교 산학협력단 Performance estimation and controlling method for ship energy saving device using digital twin
US11928103B2 (en) 2020-08-18 2024-03-12 Electronics And Telecommunications Research Institute Method and apparatus for configurating digital twin
KR102354594B1 (en) * 2020-09-22 2022-01-21 한국기술교육대학교 산학협력단 Electronic device and method for performing control software verification applied to autonomous thing
KR102433952B1 (en) * 2020-10-30 2022-08-19 한국전자기술연구원 Digital twin system using IoT platform
KR102357499B1 (en) * 2020-11-26 2022-02-07 (주)중앙티씨렌탈 Tower crane autonomous operation system and autonomous operation method thereof
KR102261942B1 (en) * 2020-12-24 2021-06-07 주식회사 페이스 Method to construct a Digital Twin by combining Reduced Order Models, Measurement Data and Machine Learning Techniques for a Multiphysical Engineering System
KR102453793B1 (en) * 2020-12-30 2022-10-12 (주)빌리언이십일 System and Method for Testing of Smart Fish Farm Controller
KR20220095692A (en) 2020-12-30 2022-07-07 상명대학교산학협력단 Simulation technology for nuclaear power plant decommission
CN113064389B (en) * 2021-03-04 2022-07-01 常州信息职业技术学院 Intelligent production line touch control system and method based on digital twinning
KR102404007B1 (en) 2021-07-20 2022-05-31 한국산업기술시험원 System for performing accelerated reinforcement learning of thermo-fluid system using digital twin technique
KR102644608B1 (en) 2021-08-23 2024-03-11 한국철도기술연구원 Camera position initialization method based on digital twin
KR102582368B1 (en) 2021-09-30 2023-09-25 주식회사 트라이텍 Cutting system using grid method
KR102477783B1 (en) * 2022-06-02 2022-12-15 이안 주식회사 Method and system for providing a metaverse base on digital twin
KR102565529B1 (en) * 2022-07-19 2023-08-14 주식회사 동양이엔씨 Autonomous control-based water treatment control system and method thereof
WO2024049180A1 (en) * 2022-08-31 2024-03-07 주식회사 엘지에너지솔루션 System for test run of facility, method therefor, and control device therefor, using digital twin
KR102474936B1 (en) * 2022-09-16 2022-12-06 주식회사 이현정보 Ai-based automatic control integrated building system using complex control sensor

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1185208A (en) * 1997-09-01 1999-03-30 Hitachi Inf Syst Ltd Event control system taking in prediction of action and correction and storage medium for the same
KR20170089146A (en) * 2016-01-26 2017-08-03 전자부품연구원 Method for building a driving scenarios of internet of things equipment
JP2017188118A (en) * 2016-04-08 2017-10-12 リープヘル−ヴェルク ネンツィング ゲーエムベーハー System for digitally supporting work process
KR20180025887A (en) * 2015-07-03 2018-03-09 어페로, 인크. System and method for Virtual Objects Internet (IoT) devices and hubs

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101960162B1 (en) 2017-05-15 2019-07-05 현대오토에버 주식회사 Building Integrated Management System and Method Based on Digital SOP and Prediction

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1185208A (en) * 1997-09-01 1999-03-30 Hitachi Inf Syst Ltd Event control system taking in prediction of action and correction and storage medium for the same
KR20180025887A (en) * 2015-07-03 2018-03-09 어페로, 인크. System and method for Virtual Objects Internet (IoT) devices and hubs
KR20170089146A (en) * 2016-01-26 2017-08-03 전자부품연구원 Method for building a driving scenarios of internet of things equipment
JP2017188118A (en) * 2016-04-08 2017-10-12 リープヘル−ヴェルク ネンツィング ゲーエムベーハー System for digitally supporting work process

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CHOI JINCHUL ET AL: "System design for configuring digital twins in a virtual enviroment", PROCEEDINGS OF THE KIISE CONFERENCE, December 2017 (2017-12-01), pages 480 - 481 *
KANG HYO EUN ET AL.: "Technology and trend of digital twin based on manufacturing industry", KICS JOURNAL ( INFORMATION AND COMMUNICATIONS MAGAZINE), vol. 35, no. 8, July 2018 (2018-07-01), pages 24 - 28 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112131782A (en) * 2020-08-27 2020-12-25 浙江大学 Multi-loop intelligent factory edge side digital twin scene coupling device
CN112131782B (en) * 2020-08-27 2024-05-14 浙江大学 Multi-loop intelligent factory edge side digital twin scene coupling device

Also Published As

Publication number Publication date
KR20200081066A (en) 2020-07-07

Similar Documents

Publication Publication Date Title
WO2020138603A1 (en) Digital twin system and method for optimizing control scenario of mechanical device
JP7078170B2 (en) How to operate industrial PC devices and industrial PC devices
KR100488647B1 (en) Control system architecture for a multi-component armament system
Codetta-Raiteri et al. Dynamic Bayesian networks for fault detection, identification, and recovery in autonomous spacecraft
US9921938B2 (en) Anomaly detection system, anomaly detection method, and program for the same
WO2012134101A2 (en) Multiple plc simulation system
WO2019083126A1 (en) Method for verifying measurement control system of nuclear power plant, and verification device therefor
CN112186900B (en) 5G technology-based integrated box operation monitoring method and device
CN108695855A (en) The computer implemented method of controller is cut down for configuration load
CN113985829A (en) Distributed industrial control system of nuclear power station and virtual and physical switching control method thereof
WO2015060676A2 (en) Building control system for integrating design and operation steps
CN113746674A (en) TCMS network fault propagation analysis method based on SIR model
WO2021080169A2 (en) Building energy integrated-management apparatus, and method therefor
CN101726691B (en) Method of inspecting the integrity of an avionics system, and an inspection device for implementing said method
CN111189354B (en) Weapon equipment maintenance training system
WO2022114634A1 (en) Device and method for tracking basis of abnormal state determination by using neural network model
US20170277175A1 (en) Test device for monitoring control device
KR102482353B1 (en) Plant management method, plant design device, and plant management device
CN110783911A (en) Soft intelligent switch configuration method and system for medium and low voltage distribution network
Chang et al. Low-cost fuzzing drone control system for configuration errors threatening flight safety in edge terminals
WO2024053913A1 (en) Simulation system and method for real-time tracking of power plant status based on power plant field values
KR20200117778A (en) The Artificial Intelligence system of Independent Combat units for operating Intelligent Grounded Force's Combat systems
WO2022086081A1 (en) Construction simulation system and method for nuclear power plant equipment
WO2024117273A1 (en) Smart factory system for diagnosing state by using time-series data and artificial intelligence
CN117278384B (en) Linkage alarm realization method, system and device based on rule chain

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19901663

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19901663

Country of ref document: EP

Kind code of ref document: A1